Search

Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learning (RL) unlocks a new axis for the continued improvement of artificial intelligence, with the promise that large language models (LLMs) can scale their training data by learning to explore with rewards. However, prior published work has not produced competitive results. In light of this, we report on the training practice of Kimi k1.5, our latest multi-modal LLM trained with RL, including its RL training techniques, multi-modal data recipes, and infrastructure optimization. Long context scaling and improved policy optimization methods are key ingredients of our approach, which establishes a simplistic, effective RL framework without relying on more complex techniques such as Monte Carlo tree search, value functions, and process reward models. Notably, our system achieves state-of-the-art reasoning performance across multiple benchmarks and modalities -- e.g., 77.5 on AIME, 96.2 on MATH 500, 94-th percentile on Codeforces, 74.9 on MathVista -- matching OpenAI's o1. Moreover, we present effective long2short methods that use long-CoT techniques to improve short-CoT models, yielding state-of-the-art short-CoT reasoning results -- e.g., 60.8 on AIME, 94.6 on MATH500, 47.3 on LiveCodeBench -- outperforming existing short-CoT models such as GPT-4o and Claude Sonnet 3.5 by a large margin (up to +550%)., Comment: 25 pages

Semi-quantum key distribution (SQKD) allows sharing random keys between a quantum user and a classical user. However, implementing classical user operations is challenging, posing a hurdle to achieving the Single-state protocol. By using the "selective modulation" method, the feasibility of SQKD is verified in principle. The proposal of the selective modulation method enables the realization of other protocols for SQKD. To advance experimental progress in SQKD, we propose and implement a phase-encoded semi-quantum key distribution system based on the Single-state protocol and the "selective modulation" method. The system operates at a frequency of 100MHz and an average photon number of 0.1. The interference contrast achieved 96.52%, the average quantum bit error rate was 1.19%, and the raw key rate reached 88Kbps. Our experimental results demonstrate the feasibility and stability of the proposed phase-encoded semi-quantum key distribution system. Furthermore, by leveraging the "selective modulation" scheme proposed in this paper, we develop a comprehensive theoretical description of selective modulation. Through an analysis of quantum state evolution, we assess the security of our system, ultimately demonstrating its resilience against attacks targeting quantum states. The classical user of our system requires only two optical devices, significantly reducing the equipment requirements and enhancing its application potential. This work validates the feasibility of semi-quantum key distribution experiments and provides ideas for future research on semi-quantum key distribution experiments and security studies.

Topological defects in magnetism have attracted great attention due to fundamental research interests and potential novel spintronics applications. Rich examples of topological defects can be found in nanoscale non-uniform spin textures, such as monopoles, domain walls, vortices, and skyrmions. Recently, skyrmions stabilized by the Dzyaloshinskii-Moriya interaction have been studied extensively. However, the stabilization of antiskyrmions is less straightforward. Here, using numerical simulations we demonstrate that antiskyrmions can be a stable spin configuration in the presence of anisotropic Dzyaloshinskii-Moriya interaction. We find current-driven antiskyrmion motion that has a transverse component, namely antiskyrmion Hall effect. The antiskyrmion gyroconstant is opposite to that for skyrmion, which allows the current-driven propagation of coupled skyrmion-antiskyrmion pairs without apparent skyrmion Hall effect. The antiskyrmion Hall angle strongly depends on the current direction, and a zero antiskyrmion Hall angle can be achieved at a critic current direction. These results open up possibilities to tailor the spin topology in nanoscale magnetism, which may be useful in the emerging field of skyrmionics., Comment: 31 pages, 6 figures, to appear in Physical Review B